Mining non-redundant association rules

Mohammed J. Zaki

Research output: Contribution to journalArticle

275 Citations (Scopus)

Abstract

The traditional association rule mining framework produces many redundant rules. The extent of redundancy is a lot larger than previously suspected. We present a new framework for associations based on the concept of closed frequent itemsets. The number of non-redundant rules produced by the new approach is exponentially (in the length of the longest frequent itemset) smaller than the rule set from the traditional approach. Experiments using several "hard" as well as "easy" real and synthetic databases confirm the utility of our framework in terms of reduction in the number of rules presented to the user, and in terms of time.

Original languageEnglish
Pages (from-to)223-248
Number of pages26
JournalData Mining and Knowledge Discovery
Volume9
Issue number3
DOIs
Publication statusPublished - 1 Nov 2004
Externally publishedYes

Fingerprint

Association rules
Redundancy
Experiments

Keywords

  • Association rule mining
  • Formal concept analysis
  • Frequent closed itemsets

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence
  • Information Systems

Cite this

Mining non-redundant association rules. / Zaki, Mohammed J.

In: Data Mining and Knowledge Discovery, Vol. 9, No. 3, 01.11.2004, p. 223-248.

Research output: Contribution to journalArticle

Zaki, Mohammed J. / Mining non-redundant association rules. In: Data Mining and Knowledge Discovery. 2004 ; Vol. 9, No. 3. pp. 223-248.
@article{710970b4e12647e89b6647c42781452a,
title = "Mining non-redundant association rules",
abstract = "The traditional association rule mining framework produces many redundant rules. The extent of redundancy is a lot larger than previously suspected. We present a new framework for associations based on the concept of closed frequent itemsets. The number of non-redundant rules produced by the new approach is exponentially (in the length of the longest frequent itemset) smaller than the rule set from the traditional approach. Experiments using several {"}hard{"} as well as {"}easy{"} real and synthetic databases confirm the utility of our framework in terms of reduction in the number of rules presented to the user, and in terms of time.",
keywords = "Association rule mining, Formal concept analysis, Frequent closed itemsets",
author = "Zaki, {Mohammed J.}",
year = "2004",
month = "11",
day = "1",
doi = "10.1023/B:DAMI.0000040429.96086.c7",
language = "English",
volume = "9",
pages = "223--248",
journal = "Data Mining and Knowledge Discovery",
issn = "1384-5810",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Mining non-redundant association rules

AU - Zaki, Mohammed J.

PY - 2004/11/1

Y1 - 2004/11/1

N2 - The traditional association rule mining framework produces many redundant rules. The extent of redundancy is a lot larger than previously suspected. We present a new framework for associations based on the concept of closed frequent itemsets. The number of non-redundant rules produced by the new approach is exponentially (in the length of the longest frequent itemset) smaller than the rule set from the traditional approach. Experiments using several "hard" as well as "easy" real and synthetic databases confirm the utility of our framework in terms of reduction in the number of rules presented to the user, and in terms of time.

AB - The traditional association rule mining framework produces many redundant rules. The extent of redundancy is a lot larger than previously suspected. We present a new framework for associations based on the concept of closed frequent itemsets. The number of non-redundant rules produced by the new approach is exponentially (in the length of the longest frequent itemset) smaller than the rule set from the traditional approach. Experiments using several "hard" as well as "easy" real and synthetic databases confirm the utility of our framework in terms of reduction in the number of rules presented to the user, and in terms of time.

KW - Association rule mining

KW - Formal concept analysis

KW - Frequent closed itemsets

UR - http://www.scopus.com/inward/record.url?scp=4444337294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4444337294&partnerID=8YFLogxK

U2 - 10.1023/B:DAMI.0000040429.96086.c7

DO - 10.1023/B:DAMI.0000040429.96086.c7

M3 - Article

VL - 9

SP - 223

EP - 248

JO - Data Mining and Knowledge Discovery

JF - Data Mining and Knowledge Discovery

SN - 1384-5810

IS - 3

ER -